结合场景分类的近岸区域SAR舰船目标快速检测方法

合成孔径雷达(Synthetic Aperture Radar, SAR)图像场景通常较大，深层卷积网络用于SAR舰船目标检测时通常需要密集滑窗提取子图像预处理，然后利用目标检测网络直接对子图像进行目标检测，该过程存在大量信息冗余，极大影响了目标检测效率的提升。在近岸区域下陆地场景偏多且场景复杂，针对以上问题，本文提出了一种结合场景分类的近岸区域SAR舰船快速目标检测方法（SC-SSD），该方法主要包含两个阶段:场景分类阶段和目标检测阶段。它们分别是由场景分类网络(Convolutional Neural Network for Scene Classification, SC-CNN)和目标检测网络(Single Shot Detector, SSD)构成。其中SC-CNN可以快速粗略筛选出可能包含舰船的子图像，然后将筛选出的子图像输入到SSD网络中实现精细化的舰船目标检测。基于高分辨率SAR舰船检测数据集AIR-SARShip-1.0的实验结果表明，提出方法相比于传统舰船检测方法，在保持较高的检测精度的同时，具有明显更快的检测速度。 

SAR Ship Target Rapid Detection Method Combined with Scene Classification in the Inshore Region

Synthetic Aperture Radar (SAR) image scene is usually large, deep convolutional network for SAR ship target detection usually requires dense sliding window to extract sub-image pre-processing, and then use the target detection network to directly target detection sub-image, the process has a large number of information redundancy, which greatly affects the efficiency of target detection. In the inshore region, there are many land scenes and complex scenes, for the above problems, this paper proposes a fast target detection method(SC-SSD) for SAR ships in the near-shore region combined with scene classification, which mainly consists of two stages: scene classification stage and target detection stage. They consist of Convolutional Neural Network for Scene Classification (SC-CNN) and Single Shot Detector (SSD), respectively. The SC-CNN can quickly and coarsely filter out the sub-images that may contain ships, and then input the filtered sub-images to the SSD network to realize fine-grained ship target detection. The experimental results based on the high-resolution SAR ship detection dataset AIR-SARShip-1.0 show that the proposed method is significantly faster than the traditional ship detection method while maintaining a higher detection accuracy.